Product · Pillar II · Protect

Guardrails that enforce your policy, not a generic one.

PromptGuard screens text. MediaGuard screens images. Both enforce bespoke policies on AI-generated or human content and return item-level verdicts, threat scores, and rationales through scalar checks or asynchronous batches.

check_prompt →Non-Compliant· threat 0.94check_media →Compliant· threat 0.06
01Two guards, two execution modes

PromptGuard for text. MediaGuard for images. Scalar or batch.

PromptGuard

Text, screened against your rules

User prompts, model outputs, agent messages, documents. Anything textual is screened for the policies you define: prohibited topics, regulated claims, brand rules, disclosure risks, and anything else your reviewers require, either in a live production path or as a server-side bulk moderation job.

POST /v1/guardrails/prompt

MediaGuard

Images, screened with the same rigor

Generated images and uploads, checked against bespoke visual policies: content categories, composition rules, brand and platform requirements. Same policy model, with scalar checks for request paths and asynchronous batches for reviews and backfills.

POST /v1/guardrails/media

Recommended PromptGuard and MediaGuard batch routes accept simple prompt strings or media URL/file-ID strings plus shared policy settings. The generic batch resource remains available for advanced provider-compatible and JSONL workflows; see the batch API documentation.

02Policy model

Hundreds of rules. One flat price.

Generic moderation categories are where policy goes to die. Guardrails run your policy, written with your team, versioned, and enforced verbatim. Customers configure 225+ custom policy rules today, and pricing stays flat no matter how many you run.

Bespoke by default

Policies reflect your obligations, not a vendor taxonomy. PromptGuard and MediaGuard tuning requires permission and stays private to the customer.

Any data

AI-generated or human-written, inbound or outbound, text or image: if it flows through your product, it can be checked.

Explained verdicts

Every check returns a compliance status, a threat level, and a rationale, so your logs answer "why" before anyone asks.

Guardrails reduce exposure, but they are only one part of a reliable system. Read our practical guide to preventing LLM hallucinations in production.

03Production record

In production today.

300,000+
AI checks per day
17 billion+
tokens screened monthly
Text + image
multimodal coverage
225+
custom policy rules per client

Built to be hard to break.

A jury, not a judge.

Each check is adjudicated by multiple models. No single model failure, provider outage, or bad response decides a verdict on its own.

Degrades in layers.

Redundant components back each other up, so a struggling dependency narrows the system instead of stopping it.

Continuity, on the record.

Served production traffic every hour for the last 90 days. A measured record, not an SLA.

Verdicts that explain themselves.

Each check is a full policy adjudication: verdict, threat score, and written rationale, not a single-classifier score.

04Comparisons

Evaluating Bedrock Guardrails or Hive AI?

Good. Run the comparison. AetherLab has been chosen over Amazon Bedrock Guardrails and Hive AI in head-to-head evaluations in high-stakes workflows. The pattern behind those decisions:

Policy fidelity

High-stakes workflows fail on the policies a fixed category list can't express. Bedrock Guardrails caps denied topics at 30 per guardrail; AetherLab customers run bespoke rule sets more than seven times that size.

Image parity

Text and image checks share one policy model and one API. Image is not a separate, weaker product.

Cost shape

Flat pricing regardless of policy count: adding your 200th rule costs the same as your 5th, which changes how thoroughly teams are willing to write policy.

We're glad to support a structured evaluation against your current stack. Request one here.

05For engineers

Live in an afternoon.

Guardrails are one pip install aetherlab away. Use check_prompt and check_media for scalar checks, or post simple items plus shared settings to the guardrail-specific batch routes for server-side bulk moderation and backfills.

prompt_batch.shREST · recommended
curl -sS -X POST \
  https://api.aetherlab.co/v1/guardrails/prompt/batches \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "items": [
      "historical text to screen",
      "a second prompt to review"
    ],
    "settings": {
      "blacklisted_keyword": "guaranteed returns",
      "reasoning_mode": "medium"
    }
  }'

Put your policy in production.

Bring your rules, or the findings from an AdversarialScan, and we'll configure guardrails against them for scalar production checks, bulk moderation, and backfills.

Ask about the Evidence Pack

Leave your email and we'll walk you through what an Evidence Pack contains for your use case: severity-scored findings, business-impact mapping, and the approval record.